Model:
Use reference images
Leave off for text-to-image. Turn on to upload or paste up to 16 reference images.
Playground ratio shorthand. API calls may use auto, a positive WIDTHxHEIGHT target, or a W:H ratio; non-auto targets are mapped to the nearest official popular size.
Resolution tier. Effective when size is an aspect ratio.
Rendering quality. Auto lets GPT-Image 2 choose for the prompt.
Number of images to generate. Credits are charged per generated image.
USD estimate $0.015-$0.03: highest recharge package uses $1 = 2,000 credits; entry package uses $1 = 1,000 credits.
History
Saved locally in this browser
0 running · 0 completed
Billing Rules
Model overview
OpenAI GPT-Image 2 supports image generation and editing for detailed commercial visuals, reference-guided composition, local revisions, and high-resolution creative production.
Start with the desired visual outcome, references, and delivery format, then shape the generation workflow around them.
APIAny exposes GPT-Image 2 through one documented API surface with live pricing, model status, request examples, and an on-page playground. Teams can evaluate the model here, then keep authentication, usage records, and production routing in the same platform.
Try GPT-Image 2 in the playground
Use cases
These workflows show where GPT-Image 2 fits in a real product. Test the same inputs in the playground, compare the output with related models, and choose the route that meets your quality, latency, and budget requirements.
01
Use GPT-Image 2 to create visual directions for launches, ads, landing pages, and social campaigns. Standardize prompts and reference assets so a team can compare variants without rebuilding the generation workflow.
Try GPT-Image 2 in the playground
02
Use natural-language instructions and reference images to revise composition, style, objects, or local details with GPT-Image 2. Keep the original brief and inputs in your workflow for repeatable review cycles.
Try GPT-Image 2 in the playground
03
Generate product scenes, catalog assets, presentation imagery, or review-ready content with GPT-Image 2. Batch requests through the API when a catalog needs consistent formats and repeatable output.
Try GPT-Image 2 in the playground
Core capabilities
The following capabilities explain the practical input, output, and workflow characteristics that matter when evaluating GPT-Image 2. Available request parameters remain visible in the live API reference on this page.
/01
Describe the requested output or task in text and send it through the documented GPT-Image 2 API request.
/02
Provide supported image inputs to guide editing, visual identity, composition, or motion in GPT-Image 2 workflows.
/03
Revise supported images with natural-language instructions while retaining the source context needed for controlled changes.
/04
Select supported quality or resolution tiers when the final GPT-Image 2 asset needs more detail for review or delivery.
/05
Use GPT-Image 2 when detail, consistency, visual coherence, or polished production quality matters more than minimum latency.
APIAny advantages
APIAny combines direct model access with the operational controls needed to move from evaluation to production without maintaining a separate integration for every provider.
Call GPT-Image 2 with an APIAny key and a documented request format. Keep your application integration stable while model versions and upstream routes evolve behind the gateway.
Review the live GPT-Image 2 pricing rules before a request, estimate credits in the playground, and inspect request-level usage records after the call completes.
Use model status, channel health, retry policy, and usage logs to operate GPT-Image 2 as part of a production workflow instead of treating it as an isolated demo.
Integration
Move from a playground test to an authenticated production request in three steps. The page keeps the model identifier, request schema, pricing, and response examples together. Treat generation as an asynchronous media pipeline with durable task tracking, validation, and asset delivery.
Sign in to APIAny, create a project API key, and assign only the model scope and budget controls your application needs.
Copy the request example from this page, set the model field to the selected GPT-Image 2 version, and send it to the documented APIAny endpoint.
Track status, latency, credits, and returned usage. Compare versions or related models with the same workload before shifting production traffic.
FAQ
Direct answers about capabilities, use cases, integration, and choosing the right GPT-Image 2 route.
OpenAI GPT-Image 2 supports image generation and editing for detailed commercial visuals, reference-guided composition, local revisions, and high-resolution creative production. APIAny makes this model callable through an authenticated API with live pricing, status information, request examples, and a browser playground on the same page.
Common GPT-Image 2 workflows include Campaign and marketing visuals, Image editing and controlled revisions, Product and catalog content. The best fit depends on the input format, output quality, latency, and cost your product requires.
Create an APIAny key, use the endpoint documented on this page, and set the request model field to the selected GPT-Image 2 version. The playground can generate a working payload before you integrate it into application code.
Compare the versions shown on this page by price, supported parameters, and capabilities such as Text prompt input, Image and reference input, Prompt-based image editing. Test a representative production input before choosing the default route.
Authentication
Every request needs a Bearer token in the Authorization header. Create an API key in the console.
Authorization: Bearer YOUR_API_KEYhttps://apiany.ai/v1/images/generationsRequest parameters
| Parameter | Type | Required | Notes |
|---|---|---|---|
model | string | Required | Model identifier to invoke. Use this model's ID. |
prompt | string | Required | Text prompt describing what you want to generate. |
size | string | Optional | Playground ratio shorthand. API calls may use auto, a positive WIDTHxHEIGHT target, or a W:H ratio; non-auto targets are mapped to the nearest official popular size. · Options: auto, 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:21 · Default: auto |
resolution | string | Optional | Resolution tier. Effective when size is an aspect ratio. · Options: 1K, 2K, 4K · Default: 1K |
quality | string | Optional | Rendering quality. Auto lets GPT-Image 2 choose for the prompt. · Options: auto, low, medium, high · Default: auto |
n | number | Optional | Number of images to generate. Credits are charged per generated image. · Range: 1–10 · Default: 1 |
callback_url | string | Optional | Optional webhook URL called when the async task finishes. |
Request example
curl "https://apiany.ai/v1/images/generations" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "A polished SaaS product screenshot mockup for an API model platform",
"size": "auto",
"resolution": "1K",
"quality": "auto",
"n": 1
}'Response example
{
"task_id": "task_abc123",
"status": "pending",
"poll_url": "/v1/tasks/task_abc123",
"request_id": "req_abc123",
"credits": {
"reserved": 1000
}
}This endpoint is asynchronous: it returns a task_id immediately. Poll the task-status endpoint until status becomes succeeded, then read the result. Generated media links stay valid for 24 hours.
